© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 69154
    Prev
    Next
    INDEX
    Explanations

    blindness related contexts

    np_acts-logits-general · gemini-2.5-flash-lite

    instances of the word "blind" and related concepts about visual impairment.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     he
    -2.73
     ”
    -2.45
     ‘
    -2.33
    籥
    -2.23
    蓠
    -2.23
    ar
    -2.22
     diğer
    -2.20
    </i>
    -2.16
     ’
    -2.16
     tüm
    -2.08
    POSITIVE LOGITS
    with
    2.86
    獁
    2.63
    滏
    2.55
    禇
    2.41
     этом
    2.31
     墊
    2.27
     siya
    2.27
     プレミアム
    2.20
     Octobre
    2.19
     Februari
    2.16
    Activations Density 0.011%

    No Known Activations